Object class recognition by unsupervised scale-invariant learning

We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).

[1]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[2]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .

[3]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Pietro Perona,et al.  A Probabilistic Approach to Object Recognition Using Local Photometry and Global Geometry , 1998, ECCV.

[5]  Takeo Kanade,et al.  Neural Network-Based Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Yali Amit,et al.  A Computational Model for Visual Selection , 1999, Neural Computation.

[7]  Pietro Perona,et al.  Unsupervised learning of models for object recognition , 2000 .

[8]  Pietro Perona,et al.  Unsupervised Learning of Models for Recognition , 2000, ECCV.

[9]  Takeo Kanade,et al.  A statistical method for 3D object detection applied to faces and cars , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[10]  Pietro Perona,et al.  Towards automatic discovery of object categories , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  William T. Freeman,et al.  On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs , 2001, IEEE Trans. Inf. Theory.

[12]  Cordelia Schmid,et al.  Constructing models for content-based image retrieval , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[13]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[14]  C. Schmid,et al.  Indexing based on scale invariant interest points , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[15]  Dan Roth,et al.  Learning a Sparse Representation for Object Detection , 2002, ECCV.

[16]  Shimon Ullman,et al.  Class-Specific, Top-Down Segmentation , 2002, ECCV.

[17]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[18]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[19]  David A. Forsyth,et al.  Planar object recognition using projective shape representation , 1995, International Journal of Computer Vision.